Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6db3e00750ce9c3876d7657804cfc2c213631eefb69f31eb2749a228e8c7aca9
+oid sha256:8c91dd01139e27c6a484a572204999668554892cbc0fc65112196712a319015a
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29614c01432c40013d7789f54fb9d4d51f8d187e4d400c7e1b90a8def18074d3
+oid sha256:338ff0cd734558fbf441ca9fc381848411c1772f3ee2bf023aea52e4fa805ea1
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86a090bc482ef5f1b83af8f13fdd6e9fe2b0babec66f75c50ea84e39461e78f9
+oid sha256:dae627a7d2298122bff578106eebf3a91e3c4a65f4b6f1686a626ab036cc9c37
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001143837575064341,
+  "epoch": 0.002287675150128682,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 11.658,
       "eval_steps_per_second": 5.834,
       "step": 3
+    },
+    {
+      "epoch": 0.0015251167667524545,
+      "grad_norm": 2.0303115844726562,
+      "learning_rate": 8e-05,
+      "loss": 11.5601,
+      "step": 4
+    },
+    {
+      "epoch": 0.0019063959584405682,
+      "grad_norm": 1.3866581916809082,
+      "learning_rate": 0.0001,
+      "loss": 10.9195,
+      "step": 5
+    },
+    {
+      "epoch": 0.002287675150128682,
+      "grad_norm": 1.8674153089523315,
+      "learning_rate": 0.00012,
+      "loss": 11.3511,
+      "step": 6
+    },
+    {
+      "epoch": 0.002287675150128682,
+      "eval_loss": 2.7706356048583984,
+      "eval_runtime": 95.9066,
+      "eval_samples_per_second": 11.522,
+      "eval_steps_per_second": 5.766,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 488624772612096.0,
+  "total_flos": 977249545224192.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null